声誉体温计

舆情风险预诊工具。单段文本快速风险评估，输出风险评分 (1-10)、风险等级 (蓝/黄/橙/红/黑)、传播力×危害力矩阵。适用于客服筛查、社交媒体预检。

This skill appears coherent and local-only, but a few practical cautions: (1) review the full script yourself before use — it processes raw text and contains extensive keyword lists (no obfuscation or network calls were found in the provided code). (2) Do not feed sensitive personal data (身份证号, 手机号, 银行卡, 密码, 等) into the tool if you are concerned about logging or storage on systems you don't control — the script itself doesn't exfiltrate data, but your environment (shell history, CI logs) might retain inputs. (3) The classifier is heuristic and lightweight; treat outputs as triage suggestions, not definitive decisions for automated crisis actions. (4) If you plan automated/agent invocation in production, run it in an isolated environment and add logging/approval gates for high-severity outputs.

Type: OpenClaw Skill Name: reputation-thermometer Version: 1.0.0 The reputation-thermometer bundle is a legitimate text analysis tool designed to assess public opinion risk. The core logic in scripts/analyze_risk.py uses keyword matching and a basic Naive Bayes classifier to evaluate sentiment, virality, and potential AI generation in provided text. There is no evidence of data exfiltration, network activity, or unauthorized command execution; the script operates entirely locally on input data and lacks any high-risk functions or prompt-injection instructions.